GC025
Artificial Intelligence (AI) for Advancing Urban Systems Science and Solutions
Session ID#: 250709
Session Description:
Urban changes—demographic shifts, new/amplified migration patterns, built-up land expansion, infrastructural changes, local-to-regional environmental changes—are driving and responding to global environmental changes. The unprecedented scale and rate of these changes and their societal impacts call for transformative approaches to understand urban systems and highlight solutions addressing multidimensional tradeoffs and synergies. State-of-the-art artificial intelligence (AI) approaches highlight tremendous potential to transform urban systems science through advancements in novel measurement, modeling and simulation, and decision support systems. This session invites innovative studies that conceptualize, develop, and/or apply artificial intelligence techniques to advance our understanding of urban systems. Relevant topics include: multimodal foundational models for urban systems; AI for urban socioeconomic and environmental measurements; AI-based urban climate emulators; AI in modeling and forecasting urban parameters: land use/cover, morphology, demographics, economic activity, transportation, climate, air pollution, heat, flooding, energy/water/materials demand; AI-based urban complexity analysis; and metrics and benchmarks for AI models’ evaluation and trustworthiness assessment.
Index Terms:
1622 Earth system modeling [GLOBAL CHANGE]
1630 Impacts of global change [GLOBAL CHANGE]
1632 Land cover change [GLOBAL CHANGE]
1942 Machine learning [INFORMATICS]
Primary Convener: Bhartendu Pandey, PhD, Oak Ridge National Laboratory, Oak Ridge, TN, United States
Conveners: Deeksha Rastogi, Oak Ridge National Laboratory, Computational Sciences and Engineering Divison, Oak Ridge, United States, Ifeanyichukwu Chidiebele Nduka, University of Texas at Austin, Jackson School of Geosciences, Austin, United States and Philipe Dias, Oak Ridge National Laboratory, GSHS, GeoAI, Oak Ridge, United States
Student/Early Career Convener: Debvrat Varshney, Oak Ridge National Laboratory, Oak Ridge, United States
A Residual Convolutional Neural Network Model For Super-resolution Urban Microclimate Modeling By Fusing Climate Model, In-situ Station, And Remote Sensing Data (1864832)
Vamsi Krishna Nippulapalli, Saint Louis University’s Earth, Environmental and Geospatial Science Department, Saint Louis, MO, UNITED STATES and Orhun Aydin, Saint Louis University, Earth, Environmental and Geospatial Science, Saint Louis, United States
Modeling Land Use Drivers of Urban Heat Islands Using Spatially Explicit Random Forest Model for Urban Planning and Remediation in the City of Saint Louis, Missouri (1865830)
Donivan James, Saint Louis University, Saint Louis, MO, UNITED STATES and Orhun Aydin, Saint Louis University, Earth, Environmental and Geospatial Science, Saint Louis, United States
Global Mapping of Individual Building Heights Using Machine Learning and Analysis of 3D Urban Morphology to Unveil Global Disparities (1907235)
Yangzi Che, Sun Yat-Sen University, Guangzhou, China, Xiaoping Liu, Sun Yat-Sen University, School of Geography and Planning, Guangzhou, China and Xuecao Li, College of Land Science and Technology, China Agricultural University, Beijing, China
Advanced Road-Segment Greenhouse Gas and Air Pollution Estimation Using Vision AI Traffic Data Fused with Real-World Sensor Measurements (1941341)
Seyoung Kim, Myongji University, Yongin-si, SOUTH KOREA, Myeonggyun KIM, Myongji University, Dept. of Environmental Engineering and Energy, Yongin, South Korea and Hyo-Jong Song, Myongji University, Dept. of Environmental Engineering and Energy, Seoul, South Korea
Transfer learning for constraining urban climate projection (1950597)
Yiwen Zhang, University of Illinois at Urbana-Champaign, Department of Civil and Environmental Engineering, Urbana, IL, United States and Lei Zhao, University of Illinois at Urbana-Champaign, Department of Civil and Environmental Engineering, Urbana, United States
WalkNet: A Vision-Based Framework for Mapping Urban Pedestrian Infrastructure (1978276)
Protik Bose Pranto, Arizona State University, School of Computing and Augmented Intelligence, Tempe, United States, Isaac Buo, Arizona State University, School of Arts, Media and Engineering, Tempe, United States and Ariane Middel, Arizona State University, Arts, Media, and Engineering (AME), Tempe, AZ, United States
Prediction of Building Energy Consumption in Urban Areas: Integrating Environmental and Morphological Context through Machine Learning (1981561)
Eunju Ji1,2, Sang Hyunk Kim3, Sunjin Kim1,2 and Dong-Kun Lee4, (1)Seoul National University, Department of Landscape Architecture and Rural Systems Engineering, College of Agriculture and Life Sciences, Seoul, Korea, Republic of (South), (2)Seoul National University, Integrated Major in Smart City Global Convergence, Seoul, Korea, Republic of (South), (3)Seoul National University, Interdisciplinary Program in Landscape Architecture, Seoul, South Korea, (4)Seoul National Universiy, Department of Landscape Architecture and Rural System Engineering, Seoul, South Korea
